[gmx-users] Performance (GMX4.6.1): MPI vs Threads

Mark Abraham mark.j.abraham at gmail.com
Thu May 16 19:26:05 CEST 2013


cmake -DGMX_THREAD_MPI=on is intended to provide maximum performance for
your case, i.e. a single node. It's on by default for a reason ;-)

Mark


On Thu, May 16, 2013 at 6:57 PM, Thomas Schlesier <schlesi at uni-mainz.de>wrote:

> Dear all,
> if one performs a parallel calculation on a single node / computer with
> more than 1 core, is there a speed difference between MPI and Threads?
>
> Problem is for gromacs 4.6.1 i'm facing problems to link it to OpenMpi. A
> serial version (without threads) worked, so i think i should be able to
> compile a version which supports threads.
> Since we only run calculations on a single node on our cluster (no
> infini-band), i'm wondering if the programm with threads would be
> sufficient in our case.
>
> Greetings
> Thomas
> --
> gmx-users mailing list    gmx-users at gromacs.org
> http://lists.gromacs.org/**mailman/listinfo/gmx-users<http://lists.gromacs.org/mailman/listinfo/gmx-users>
> * Please search the archive at http://www.gromacs.org/**
> Support/Mailing_Lists/Search<http://www.gromacs.org/Support/Mailing_Lists/Search>before posting!
> * Please don't post (un)subscribe requests to the list. Use the www
> interface or send it to gmx-users-request at gromacs.org.
> * Can't post? Read http://www.gromacs.org/**Support/Mailing_Lists<http://www.gromacs.org/Support/Mailing_Lists>
>



More information about the gromacs.org_gmx-users mailing list